metadata
base_model: microsoft/resnet-101
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: ResNet Model (model_idx_0081)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | ResNet |
| Split | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 81 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9644 |
| Val Accuracy | 0.8797 |
| Test Accuracy | 0.8826 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, apple, wardrobe, television, worm, mouse, camel, plain, telephone, girl, bee, bus, orchid, castle, chair, bowl, bear, caterpillar, mushroom, snail, flatfish, seal, cup, streetcar, mountain, trout, sea, motorcycle, lamp, rocket, bottle, maple_tree, lawn_mower, whale, road, lobster, oak_tree, boy, rose, table, plate, man, butterfly, otter, ray, keyboard, porcupine, cattle, tractor, tulip